{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.063644289970398, "min": 1.063644289970398, "max": 2.863027572631836, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10167.3759765625, "min": 10167.3759765625, "max": 29320.265625, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 11.688468933105469, "min": 0.3225710391998291, "max": 11.688468933105469, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2279.25146484375, "min": 62.57878112792969, "max": 2354.90234375, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06487245531774105, "min": 0.05897610750368995, "max": 0.07332217991635986, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2594898212709642, "min": 0.2359044300147598, "max": 0.35784598209840407, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19682773370660986, "min": 0.12474709655633015, "max": 0.28239769985278446, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7873109348264394, "min": 0.4989883862253206, "max": 1.3766376437509762, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 22.704545454545453, "min": 3.4318181818181817, "max": 23.01818181818182, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 999.0, "min": 151.0, "max": 1266.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 22.704545454545453, "min": 3.4318181818181817, "max": 23.01818181818182, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 999.0, "min": 151.0, "max": 1266.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1723565418", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1723566014" }, "total": 595.814592507, "count": 1, "self": 0.5925340010002174, "children": { "run_training.setup": { "total": 0.08078149099992515, "count": 1, "self": 0.08078149099992515 }, "TrainerController.start_learning": { "total": 595.1412770149999, "count": 1, "self": 0.8728783499965402, "children": { "TrainerController._reset_env": { "total": 3.9009409430000233, "count": 1, "self": 3.9009409430000233 }, "TrainerController.advance": { "total": 590.2607839070033, "count": 18202, "self": 0.4219841580256798, "children": { "env_step": { "total": 589.8387997489776, "count": 18202, "self": 453.35172407498237, "children": { "SubprocessEnvManager._take_step": { "total": 136.06979897499912, "count": 18202, "self": 2.685935944996686, "children": { "TorchPolicy.evaluate": { "total": 133.38386303000243, "count": 18202, "self": 133.38386303000243 } } }, "workers": { "total": 0.4172766989961474, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 593.1613695689911, "count": 18202, "is_parallel": true, "self": 280.8764112710031, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00695257400002447, "count": 1, "is_parallel": true, "self": 0.004571378000150617, "children": { "_process_rank_one_or_two_observation": { "total": 0.002381195999873853, "count": 10, "is_parallel": true, "self": 0.002381195999873853 } } }, "UnityEnvironment.step": { "total": 0.08093822700004694, "count": 1, "is_parallel": true, "self": 0.0008727940000881063, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042532700001629564, "count": 1, "is_parallel": true, "self": 0.00042532700001629564 }, "communicator.exchange": { "total": 0.06895696499998394, "count": 1, "is_parallel": true, "self": 0.06895696499998394 }, "steps_from_proto": { "total": 0.010683140999958596, "count": 1, "is_parallel": true, "self": 0.008619115999977112, "children": { "_process_rank_one_or_two_observation": { "total": 0.002064024999981484, "count": 10, "is_parallel": true, "self": 0.002064024999981484 } } } } } } }, "UnityEnvironment.step": { "total": 312.28495829798794, "count": 18201, "is_parallel": true, "self": 15.17905934598889, "children": { "UnityEnvironment._generate_step_input": { "total": 7.635910442984027, "count": 18201, "is_parallel": true, "self": 7.635910442984027 }, "communicator.exchange": { "total": 245.1327027720015, "count": 18201, "is_parallel": true, "self": 245.1327027720015 }, "steps_from_proto": { "total": 44.33728573701353, "count": 18201, "is_parallel": true, "self": 8.882486088032579, "children": { "_process_rank_one_or_two_observation": { "total": 35.45479964898095, "count": 182010, "is_parallel": true, "self": 35.45479964898095 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00027731099999073194, "count": 1, "self": 0.00027731099999073194, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 583.2413221059425, "count": 780008, "is_parallel": true, "self": 18.39540012392672, "children": { "process_trajectory": { "total": 317.9130307410163, "count": 780008, "is_parallel": true, "self": 316.9729794200164, "children": { "RLTrainer._checkpoint": { "total": 0.9400513209999417, "count": 4, "is_parallel": true, "self": 0.9400513209999417 } } }, "_update_policy": { "total": 246.93289124099942, "count": 90, "is_parallel": true, "self": 71.1777219399911, "children": { "TorchPPOOptimizer.update": { "total": 175.75516930100832, "count": 4587, "is_parallel": true, "self": 175.75516930100832 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1063965040000312, "count": 1, "self": 0.0013329040000371606, "children": { "RLTrainer._checkpoint": { "total": 0.10506359999999404, "count": 1, "self": 0.10506359999999404 } } } } } } }